Marco A. Acevedo Zamora
This work will use Artificial Intelligence tools for polymetallic ore and gangue characterization that are promising for revolutionizing microscopic studies of thin/thick sections (Petrography), a common ground between Industry and Academia, benefiting geological studies and the society.
We want to develop new data acquisition (1st work package, WP1) and analysis tool software (2nd work package, WP2) to elaborate empirical models for predicting trace element behavior. The WP1 is scheduled for the
By characterizing and modeling trace elements in a pilot software platform, we are looking forward to
Acevedo, M. (2016). Emplacement and Magmatic Evolution of the Val Fredda Complex intrusions (southern Adamello Batholith, N. Italy). MSc in Geology thesis archive, 177 p., University of Geneva (UNIGE). https://archive-ouverte.unige.ch/pages/masters?all_subtypes=0
Acevedo, M. (2020). “Novel ways of automated trace element-mineral association recognition.” Manuscript accepted in Conference in Minerals Engineering, February 2020. Lulea, Sweden.
Deep Learning specialization. Andrew Ng. at Coursera online (Aug 2020).
Machine Learning: Introduction to Artificial Intelligence in MatLab with Andrew Ng. (Stanford University) at Coursera online (Jan 2019)..